Lossy compression algorithms are widely used in video coding. However, lossy compressed videos exist some annoying distortion and artifacts, such as blocking, blurring, and ringing. Thus, coding efficiency improvement is a steady-state topic in the domain of video coding. High Efficiency Video Coding (HEVC), a recent video standard, adopts two in-loop filters for the improvement of the coding efficiency, including deblocking (DB) and sample adaptive offset (SAO). In a certain extent, traditional in-loop filters reduce the distortion and improve the video quality. But the reduction of the distortion is a nonlinear problem that is difficult to be solved by traditional linear filters. Recently, the progress of deep learning shows the possibility to settle the complex problems in the computer vision field. Meanwhile, according to the compressive sensing theory, the post-processing method at the decoder end can further enhance the coding efficiency. In this paper, we propose a variable-filter-size Residue-learning convolutional neural network with batch normalization layer (VRCNN-BN). Our model is an end-to-end model. We feed the decoded pictures to the model at the decoder end. Different from previous methods, we apply the model to luma pictures and chroma pictures, respectively. In order to comprehensively evaluate the coding performance of both luma and chroma components, the color-sensitivity-based combined PSNR (CS-PSNR) is exploited to measure the effectiveness of the proposed method. Compared to HEVC baseline, our approach achieves an average BD-rate reduction of 10.3%, 8.9%, 13.1% and 11.8% in terms of CS-PSNR for random access, all intra, low delay P and low delay B configurations, respectively. Abundant experimental results indicate that our method is better than existing similar methods.

With the help of deep neural networks, video super-resolution (VSR) has made a huge breakthrough. However, these deep learning-based methods are rarely used in specific situations. In addition, training sets may not be suitable because many methods only assume that under ideal circumstances, low-resolution (LR) datasets are downgraded from high-resolution (HR) datasets in a fixed manner. In this paper, we proposed a model based on Generative Adversarial Network (GAN) and edge enhancement to perform super-resolution (SR) reconstruction for LR and blur videos, such as closed-circuit television (CCTV). The adversarial loss allows discriminators to be trained to distinguish between SR frames and ground truth (GT) frames, which is helpful to produce realistic and highly detailed results. The edge enhancement function uses the Laplacian edge module to perform edge enhancement on the intermediate result, which helps further improve the final results. In addition, we add the perceptual loss to the loss function to obtain a higher visual experience. At the same time, we also tried training network on different datasets. A large number of experiments show that our method has advantages in the Vid4 dataset and other LR videos.

Dynamic accurate heart-rate (HR) estimation using a photoplethysmogram (PPG) during intense physical activities is always challenging due to corruption by motion artifacts (MAs). It is difficult to reconstruct a clean signal and extract HR from contaminated PPG. This paper proposes a robust HR-estimation algorithm framework that uses one-channel PPG and tri-axis acceleration data to reconstruct the PPG and calculate the HR based on features of the PPG and spectral analysis. Firstly, the signal is judged by the presence of MAs. Then, the spectral peaks corresponding to acceleration data are filtered from the periodogram of the PPG when MAs exist. Different signal-processing methods are applied based on the amount of remaining PPG spectral peaks. The main MA-removal algorithm (NFEEMD) includes the repeated single-notch filter and ensemble empirical mode decomposition. Finally, HR calibration is designed to ensure the accuracy of HR tracking. The NFEEMD algorithm was performed on the 23 datasets from the 2015 IEEE Signal Processing Cup Database. The average estimation errors were 1.12 BPM (12 training datasets), 2.63 BPM (10 testing datasets) and 1.87 BPM (all 23 datasets), respectively. The Pearson correlation was 0.992. The experiment results illustrate that the proposed algorithm is not only suitable for HR estimation during continuous activities, like slow running (13 training datasets), but also for intense physical activities with acceleration, like arm exercise (10 testing datasets).

Versatile video coding (VVC) achieves enormous improvement over the advanced high efficiency video coding (HEVC) standard due to the adoption of the quadtree with nested multi-type tree (QTMT) partition structure and other coding tools. However, the computational complexity increases dramatically as well. To tackle this problem, we propose a decision tree accelerated coding tree units (CTU) partition algorithm for intra prediction in VVC. Firstly, specially designated image features are extracted to characterize the coding unit (CU) complexity. Then, the trained decision tree is employed to predict the partition results. Finally, based on our newly designed intra prediction framework, the partition process is early terminated or redundant partition modes are screened out. The experimental results show that the proposed algorithm could achieve around 52% encoding time reduction for various test video sequences on average with only 1.75% Bjontegaard delta bit rate increase compared with the reference test model VTM9.0 of VVC.